Plugins

Full sidebar workbench with file rendering and editing, terminal, Git, and subagents; third-party plugins can register new tabs.

Sidebar: file rendering/terminal/Git/subagents/custom APIs.

Hire Google's Antigravity CLI (agy) as a fast Gemini staffer for Claude Code, OpenAI Codex, and DeepSeek Harness.

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

Adds a summonable domain-expert roster that runs as subagents while the parent session keeps the task and final answer.

Pi Host ABI compatibility engine: after one install, unmodified Pi extensions from npm mount as native DSH plugins with `dsh plugin add <pi-package>`. Verified end to end on stock DSH with pi-mcp-adapter (full MCP manager: OAuth, resources, prompts, MCP Apps, elicitation, sampling), @tintinweb/pi-subagents, pi-code, pi-hermes-memory and pi-background-tasks; `pi2dsh inspect` reports a package's compatibility before installing.

Dispatch work to DSH agents from Claude Code or Codex: native subagent progress, in-host worker sessions with per-tier presets, and a multimodal bridge for vision and image generation.

Delegate bounded coding tasks to a headless CLI agent (WorkBuddy by default, or codex, claude, aider or a custom command) and collect a structured result plus the real diff, with a writable-path whitelist, a dispatch lock over overlapping paths, an isolated worktree and a structured needs_human flag. Requires Python 3.10+ (standard library only) and one installed CLI executor (WorkBuddy/CodeBuddy by default, or codex, claude, aider or a custom command).

baro as a DeepSeek Harness subagent provider: delegate a multi-story goal, get parallel execution, independent review and a verified outcome back — with a live run panel in the sidebar

Lets the agent scan Bilibili through a subagent and report what is worth watching, with per-video notes, a card wall, and an inbox for mentions, replies and shared videos.

Phone client for DeepSeek Harness — no app to install (PWA). Read sessions, background jobs, subagents, goal rounds, workflows and pending approvals, and talk to any session from it: streamed replies, tool-call progress, stop at any time, switch sessions and models. Also ships a GUI sidebar panel. Formerly dsh-taskwatch; the npm package is now dsh-in-hand.

Execution maze for DSH sessions: the agent's real path — main advance, failed or dead-end detours, backtracks, request retries and subagent branches — drawn on one wall-clock timeline, with three tracks under each lane sharing that axis (tool-call density, token pulse, context pressure) and a deterministic analysis panel below it (tool result matrix, failure-recovery chains, duration distribution); watch it grow live in a session tab, or upload up to 5 session logs for a same-axis compare.

Research-assistant plugin suite (literature search, research wiki, LaTeX compile, independent subagent review) for the DeepSeek Harness

A DSH-first Rust/ratatui agent TUI with streamed tool calls, subagents, durable sessions, and a Cordis-extensible client UI.

Skill-driven harness/loop engineering workflow agent plugin.

One settings panel managing MCP, skills, memory, subagents, prompts and sessions; customize scene combos to switch the whole environment; the Agent can also operate this plugin for you.

Trace Compare & Live Maze: draw the agent's real exploration — main path, failed or dead-end detours, backtracks, and subagent branches — on one wall-clock timeline; upload 1–2 session logs for a same-axis compare, or watch it grow live in a session tab.

A personal usage profile page in the DSH sidebar, folded from this machine's own session logs through ctx.sessionQuery. Five headline numbers (tokens with a small trend and the change against the previous period, spend, longest task, the active-day streak with your best, today's cache hit rate), a 12-month activity grid in daily / weekly / running-total views, a model-family chart by day, week or month as stacked columns or a share pie (version and tier stay apart, and vendor-specific ids collapse correctly), a token-stats ring chart of where the tokens went (system prompt, tool definitions, user messages, injected context, skills, tool calls, reasoning, answers), tokens and spend per project with the subagent share, and a per-provider split with each route's own hit rate and spend. A range switch in the header (today, this week, this month, all time or custom dates) drives the token and spend numbers, the token stats, the projects and the providers, and the selected range exports as CSV or JSON. Spend is priced at bundled list prices (peak and off-peak hours for DeepSeek direct); each provider can be set to list price, a discount, a monthly plan or not counted, stored only on this machine. The only outbound request is a six-hourly read of this package's own version from npm for the in-panel update button - no telemetry, no credentials, nothing uploaded.

A Multitask agent preset where the main conversation only plans, briefs subagents and summarizes results, while file reads, commands, search and builds run inside subagent contexts; four worker kinds, an approval gate for dangerous operations, and zero changes to DSH source.

Skill-driven harness/loop engineering workflow agent plugin.

Visually configure an agent's prompt, tools, visible skills, subagents and fallback models, and assemble several of them into a team. It never writes or edits any host preset file.

Deep reading & summarization for DSH: books/papers/videos/web into structured Obsidian notes via plugin parsers, MapReduce parallel deep-read subagents, JSON Schema outputs and an idempotent cache.

All seven Kimi ask/review/challenge/rescue/pursue/swarm/swarm-write providers through the local Kimi Code CLI, with managed hooks, jobs, budgets, and artifacts; also supports Claude Code and Codex.

Permanently delete DSH conversations with optional recursive deletion of forked and subagent sessions.